CN113344874A - Pedestrian boundary crossing detection method based on Gaussian mixture modeling - Google Patents
Pedestrian boundary crossing detection method based on Gaussian mixture modeling Download PDFInfo
- Publication number
- CN113344874A CN113344874A CN202110627647.7A CN202110627647A CN113344874A CN 113344874 A CN113344874 A CN 113344874A CN 202110627647 A CN202110627647 A CN 202110627647A CN 113344874 A CN113344874 A CN 113344874A
- Authority
- CN
- China
- Prior art keywords
- image
- foreground
- gaussian mixture
- area
- boundary crossing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 239000000203 mixture Substances 0.000 title claims abstract description 34
- 238000012544 monitoring process Methods 0.000 claims abstract description 38
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 238000012216 screening Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 11
- 230000000877 morphologic effect Effects 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 230000003628 erosive effect Effects 0.000 claims description 3
- 238000009432 framing Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000010339 dilation Effects 0.000 claims description 2
- 239000011800 void material Substances 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a pedestrian boundary crossing detection method based on Gaussian mixture modeling, which comprises the following steps: step1, acquiring a dynamic monitoring video of a monitoring area through an image acquisition device, and preprocessing the dynamic monitoring video; step2, analyzing the preprocessed image information, setting forbidden zone boundary vertexes for the zone edges forbidden to cross the border, and connecting adjacent boundary vertexes to obtain a closed boundary line of the forbidden zone; step3, constructing a Gaussian mixture model, acquiring a moving target contour in the preprocessed current frame image, and screening out the moving target contour of which the minimum circumscribed rectangle area is larger than an area threshold value; and Step4, counting foreground proportion values of the moving target contour in the area forbidden to cross the border and the duration time greater than the foreground proportion threshold, alarming when the duration time is greater than a set threshold, and continuously detecting if the duration time is not greater than the set threshold.
Description
Technical Field
The invention relates to the technical field of safety monitoring, in particular to a pedestrian boundary crossing detection method based on Gaussian mixture modeling.
Background
With the continuous development of computer vision technology, the intelligent video monitoring technology is also receiving much attention, which relates to a plurality of disciplinary knowledge such as computer vision, image processing, artificial intelligence, mode identification, etc., and the intelligent video monitoring system is different from the traditional monitoring system in intelligence, realizes the detection, identification and tracking of moving objects in a monitoring scene by automatically analyzing the content of monitoring video, and finally realizes the detection of object behaviors. Therefore, how to timely and accurately detect whether a person invades a dangerous area or a forbidden area and carry out alarm linkage to avoid tragedies is very important, and based on the method, the pedestrian boundary crossing detection method based on Gaussian mixture modeling is provided.
In summary, it is an urgent need to solve the problem of the skilled person in the art to provide a pedestrian boundary crossing detection method based on gaussian mixture modeling, which can improve the boundary crossing detection accuracy and speed, has less calculation amount, and can perform online and offline alarm in time.
Disclosure of Invention
In order to solve the above-mentioned problems and needs, the present solution provides a pedestrian boundary crossing detection method based on gaussian mixture modeling, which can solve the above technical problems due to the following technical solutions.
In order to achieve the purpose, the invention provides the following technical scheme: a pedestrian boundary crossing detection method based on Gaussian mixture modeling comprises the following steps: step1, acquiring a dynamic monitoring video of a monitoring area through an image acquisition device, and storing the dynamic monitoring video to a cache preprocessing module for video image preprocessing;
step2, analyzing the preprocessed image information, setting forbidden zone boundary vertexes for the zone edges forbidden to cross the border, and connecting adjacent boundary vertexes to obtain a closed boundary line of the forbidden zone;
step3, constructing a Gaussian mixture model, acquiring moving target contours in the preprocessed current frame image, setting an area threshold, acquiring the minimum circumscribed rectangle area and the minimum circumscribed rectangle central point of each moving target contour, and screening out the moving target contours with the minimum circumscribed rectangle areas larger than the area threshold;
and Step4, setting a foreground proportion threshold value and a timer threshold value, counting foreground proportion values of the moving target contour in the area forbidden to cross the boundary and the duration time greater than the foreground proportion threshold value, alarming when the duration time is greater than the set threshold value, and if not, continuing to detect.
Furthermore, the image acquisition device comprises a high-definition infrared camera and a monitoring control device, the high-definition infrared camera is used for acquiring image information in a monitoring area and transmitting the image information to the cache preprocessing module for image preprocessing in the border-crossing monitoring area, and the monitoring control device is used for adjusting light compensation, angle and focal length parameters of the high-definition infrared camera and carrying out fault detection and on-off control on the high-definition infrared camera.
Still further, the pre-processing comprises: and carrying out continuous image acquisition according to a user instruction, then carrying out accumulation and calculation on the continuously acquired images, calculating the average value of the accumulated images, taking the average image of the images selected by the user as an initialized image of the Gaussian mixture model, carrying out framing and graying processing on the received monitoring video image, and inputting the processed image into a detection system for border crossing detection.
Further, a safety flag of the moving object located inside and outside the forbidden area closed boundary line is set, the safety flag of the moving object located inside the boundary line is set to be 1, and the safety flag of the moving object located outside the boundary line is set to be 0.
Further, the constructing the gaussian mixture model comprises: firstly, performing background modeling on a current monitoring scene through a background modeling method, and establishing a mixed Gaussian model for each pixel point; for the newly acquired current frame image, comparing the current frame image with a background model to determine the foreground and background of the current frame image, namely pixel classification, and storing the result in a foreground image; and then optimizing the foreground image through morphological operation, and removing a small interference area of a non-pedestrian in the foreground image through a scale filter.
Still further, the pixel classification includes: and acquiring a newly read image frame, judging each pixel point, marking the corresponding pixel point as a background in the foreground image if the pixel point meets a background model of the point, and otherwise marking the corresponding pixel point as a foreground, namely a moving target.
Further, the determining each pixel point includes: firstly, initializing the mean value, standard deviation and weight of each Gaussian mixture model to obtain model initialization matrix parameters; acquiring a T frame image in a video, and obtaining a mean value, a standard deviation and a weight of each pixel point by adopting an online EM (effective noise) algorithm; detecting a newly read image frame, and sequencing each Gaussian kernel from large to small by dividing a weight w by a standard deviation sigma for each pixel point; then selecting the first B gaussians to ensure that
Eliminating noise points in the training process, wherein T is a set threshold; if only one Gaussian component in the pixel values of the current pixel point meets the following conditions:
is considered as a background point, where μiAnd (4) setting N as a mean value, updating the background image by using an online EM algorithm, and assigning the foreground as 255 and the background as 0 to obtain a foreground binary image.
Furthermore, the morphological operation comprises removing the remaining isolated points in the image by using morphological erosion and dilation operations on the foreground image, and filling the hollow area.
Further, the removing of the small interference area of the non-pedestrian in the foreground image by the scale filter includes counting the number of pixels in each small area, and removing the small non-attention area by the scale filter, wherein the size of the scale filter is set to be 30.
Furthermore, a foreground proportion value, namely a foreground pixel area ratio, of the moving target profile in an area where boundary crossing is forbidden is counted, when the foreground pixel area ratio value is larger than a set threshold value, a timer times, if the counted time is larger than the set threshold value, boundary crossing is judged, boundary crossing alarming is conducted, the boundary crossing alarming comprises online marking alarming and site alarming, online marking alarming recording is conducted according to a set safety mark, and the site alarming comprises a voice alarming device and a display reminding device; the voice warning device comprises a single chip microcomputer, a power supply module, a voice synthesizer, a loudspeaker and a wireless communication module, wherein the loudspeaker is electrically connected with the voice synthesizer, the single chip microcomputer controls the voice synthesizer to play set abnormal reminding voice through the loudspeaker, the power supply module comprises an EMI filter, a rectifier bridge and a DC-DC converter, the input end of the EMI filter is connected with a mains supply output end, the EMI filter, the rectifier bridge and the DC-DC converter are electrically connected in sequence, and the power supply module is used for providing required electric energy for the voice warning device; the display reminding device comprises an LED display screen and an LED display screen driver, the LED display screen driver is electrically connected with the LED display screen, and the LED display screen is used for displaying abnormal alarm data in a rolling mode.
According to the technical scheme, the invention has the beneficial effects that: the method can improve the accuracy and speed of border crossing detection, has less calculation amount, and can give an alarm online and offline in time.
In addition to the above objects, features and advantages, preferred embodiments of the present invention will be described in more detail below with reference to the accompanying drawings so that the features and advantages of the present invention can be easily understood.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments of the present invention or the prior art will be briefly described, wherein the drawings are only used for illustrating some embodiments of the present invention and do not limit all embodiments of the present invention thereto.
FIG. 1 is a schematic diagram of specific steps of a pedestrian boundary crossing detection method based on Gaussian mixture modeling.
Fig. 2 is a schematic diagram illustrating specific steps of the pixel classification process in this embodiment.
Fig. 3 is a flowchart illustrating a pedestrian boundary crossing detection process based on gaussian mixture modeling in this embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of specific embodiments of the present invention. Like reference symbols in the various drawings indicate like elements. It should be noted that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention without any inventive step, are within the scope of protection of the invention.
When a pedestrian appears in a scene, a monitoring picture different from the background appears, a pixel point of the position of the pedestrian is called a foreground pixel, a pixel of the monitoring background is called a background pixel, and a foreground area of the pedestrian is a key point concerned by the system. In places where pedestrians are prohibited to approach such as environment monitoring points and power supply stations and places where the flow of people is dense and the pedestrians need to be prevented from crossing the boundary such as railway stations and airports, an off-boundary detection and alarm system which can improve the accuracy and speed of off-boundary detection, has less calculation amount and can timely perform on-line and off-line alarm is needed to timely prevent the dangerous off-boundary situation from occurring, as shown in fig. 1 to 3, the pedestrian crossing detection method based on Gaussian mixture modeling specifically comprises the following steps: and Step1, acquiring the dynamic monitoring video of the monitoring area through the image acquisition device, and storing the dynamic monitoring video to a cache preprocessing module for video image preprocessing.
In this embodiment, the image acquiring device includes a high-definition infrared camera and a monitoring control device, the high-definition infrared camera is used for acquiring image information in a monitoring area and transmitting the image information to the cache preprocessing module for image preprocessing in the out-of-range monitoring area, the monitoring control device is used for adjusting light compensation, angle and focal length parameters of the high-definition infrared camera and performing fault detection and on-off control on the high-definition infrared camera, and the monitoring control device specifically includes a work control module and an intelligent pan-tilt module, the work control module includes an intelligent controller, and the intelligent controller includes a relay access point, the relay access point forms a corresponding branch circuit channel, and controls on-off of the branch circuit channel so as to control a camera power-on switch connected to the branch circuit channel, the intelligent holder module is used for adjusting light compensation, angle and focal length parameters of the high-definition infrared camera. And the pre-treatment comprises: and carrying out continuous image acquisition according to a user instruction, then carrying out accumulation and calculation on the continuously acquired images, calculating the average value of the accumulated images, taking the average image of the images selected by the user as an initialized image of the Gaussian mixture model, carrying out framing and graying processing on the received monitoring video image, and inputting the processed image into a detection system for border crossing detection.
And Step2, analyzing the preprocessed image information, setting forbidden zone boundary vertexes on the edge of the forbidden out-of-range area, connecting adjacent boundary vertexes to obtain a forbidden zone closed boundary line, and setting safety signs of moving targets positioned inside and outside the forbidden zone closed boundary line, wherein the safety sign of the moving targets positioned inside the boundary line is set to be 1, and the safety sign of the moving targets positioned outside the boundary line is set to be 0.
Step3, constructing a Gaussian mixture model, acquiring the moving target contours in the preprocessed current frame image, setting an area threshold, acquiring the minimum circumscribed rectangle area and the minimum circumscribed rectangle central point of each moving target contour, and screening the moving target contours with the minimum circumscribed rectangle areas larger than the area threshold.
The constructing of the Gaussian mixture model comprises the following steps: firstly, performing background modeling on a current monitoring scene through a background modeling method, and establishing a mixed Gaussian model for each pixel point; for the newly acquired current frame image, comparing the current frame image with a background model to determine the foreground and background of the current frame image, namely pixel classification, and storing the result in a foreground image; and then optimizing the foreground image through morphological operation, and removing a small interference area of a non-pedestrian in the foreground image through a scale filter.
As shown in fig. 2, the pixel classification includes: acquiring a newly read image frame, and judging each pixel point; if the pixel point meets the background model of the point, the corresponding pixel point is marked as the background in the foreground image, otherwise, the corresponding pixel point is marked as the foreground, namely the moving target. The judging of each pixel point comprises: a. firstly, initializing the mean value, standard deviation and weight of each Gaussian mixture model to obtain model initialization matrix parameters; b. acquiring a T frame image in a video, and obtaining a mean value, a standard deviation and a weight of each pixel point by adopting an online EM (effective noise) algorithm; c. detecting a newly read image frame, and sequencing each Gaussian kernel from large to small by dividing a weight w by a standard deviation sigma for each pixel point; d. then selecting the first B gaussians to ensure that
Eliminating noise points in the training process, wherein T is a set threshold; e. if only one Gaussian component in the pixel values of the current pixel point meets the following conditions:
is considered as a background point, where μiAnd (4) setting N as a mean value, updating the background image by using an online EM algorithm, and assigning the foreground as 255 and the background as 0 to obtain a foreground binary image. And the morphological operation comprises removing the remaining isolated points in the foreground image by adopting morphological erosion and expansion operations, and filling the hollow area. The scale filter removes foreground imagesThe small interference area of the middle non-pedestrian comprises the steps of counting the number of pixels in each small area, removing the small non-attention area by adopting a scale filter, and setting the size of the scale filter to be 30.
And Step4, setting a foreground proportion threshold value and a timer threshold value, counting foreground proportion values of the moving target contour in the area forbidden to cross the boundary and the duration time greater than the foreground proportion threshold value, alarming when the duration time is greater than the set threshold value, and if not, continuing to detect. The method comprises the steps that a foreground proportion value, namely a foreground pixel area ratio, of a moving target contour in an area where boundary crossing is forbidden is counted, when the foreground pixel area ratio value is larger than a set threshold value, a timer times, if the counted time is larger than the set threshold value, boundary crossing is judged, boundary crossing alarming is conducted, the boundary crossing alarming comprises online marking alarming and site alarming, online marking alarming recording is conducted according to set safety marks through the online marking alarming, and the site alarming comprises a voice alarming device and a display reminding device; the voice warning device comprises a single chip microcomputer, a power supply module, a voice synthesizer, a loudspeaker and a wireless communication module, wherein the loudspeaker is electrically connected with the voice synthesizer, the single chip microcomputer controls the voice synthesizer to play set abnormal reminding voice through the loudspeaker, the power supply module comprises an EMI filter, a rectifier bridge and a DC-DC converter, the input end of the EMI filter is connected with a mains supply output end, the EMI filter, the rectifier bridge and the DC-DC converter are electrically connected in sequence, and the power supply module is used for providing required electric energy for the voice warning device; the display reminding device comprises an LED display screen and an LED display screen driver, the LED display screen driver is electrically connected with the LED display screen, and the LED display screen is used for displaying abnormal alarm data in a rolling mode.
It should be noted that the described embodiments of the invention are only preferred ways of implementing the invention, and that all obvious modifications, which are within the scope of the invention, are all included in the present general inventive concept.
Claims (10)
1. A pedestrian boundary crossing detection method based on Gaussian mixture modeling is characterized by comprising the following steps:
step1, acquiring a dynamic monitoring video of a monitoring area through an image acquisition device, and storing the dynamic monitoring video to a cache preprocessing module for video image preprocessing;
step2, analyzing the preprocessed image information, setting forbidden zone boundary vertexes for the zone edges forbidden to cross the border, and connecting adjacent boundary vertexes to obtain a closed boundary line of the forbidden zone;
step3, constructing a Gaussian mixture model, acquiring moving target contours in the preprocessed current frame image, setting an area threshold, acquiring the minimum circumscribed rectangle area and the minimum circumscribed rectangle central point of each moving target contour, and screening out the moving target contours with the minimum circumscribed rectangle areas larger than the area threshold;
and Step4, setting a foreground proportion threshold value and a timer threshold value, counting foreground proportion values of the moving target contour in the area forbidden to cross the boundary and the duration time greater than the foreground proportion threshold value, alarming when the duration time is greater than the set threshold value, and if not, continuing to detect.
2. The pedestrian boundary crossing detection method based on Gaussian mixture modeling according to claim 1, wherein the image acquisition device comprises a high-definition infrared camera and a monitoring control device, the high-definition infrared camera is used for acquiring image information in a monitored area and transmitting the image information to the cache preprocessing module for image preprocessing in the boundary crossing monitored area, and the monitoring control device is used for adjusting light compensation, angle and focal length parameters of the high-definition infrared camera and performing fault detection and on-off control on the high-definition infrared camera.
3. The pedestrian boundary crossing detection method based on Gaussian mixture modeling according to claim 2, wherein the preprocessing comprises: and carrying out continuous image acquisition according to a user instruction, then carrying out accumulation and calculation on the continuously acquired images, calculating the average value of the accumulated images, taking the average image of the images selected by the user as an initialized image of the Gaussian mixture model, carrying out framing and graying processing on the received monitoring video image, and inputting the processed image into a detection system for border crossing detection.
4. The pedestrian boundary crossing detection method based on Gaussian mixture modeling according to claim 3, wherein safety flags that moving objects are located inside and outside the forbidden region closed boundary line are set, the safety flag that moving objects are located inside the boundary line is set to 1, and the safety flag that moving objects are located outside the boundary line is set to 0.
5. The pedestrian boundary crossing detection method based on Gaussian mixture modeling according to claim 4, wherein the constructing of the Gaussian mixture model comprises: firstly, performing background modeling on a current monitoring scene through a background modeling method, and establishing a mixed Gaussian model for each pixel point; for the newly acquired current frame image, comparing the current frame image with a background model to determine the foreground and background of the current frame image, namely pixel classification, and storing the result in a foreground image; and then optimizing the foreground image through morphological operation, and removing a small interference area of a non-pedestrian in the foreground image through a scale filter.
6. The pedestrian boundary crossing detection method based on Gaussian mixture modeling according to claim 5, wherein the pixel classification comprises: and acquiring a newly read image frame, judging each pixel point, marking the corresponding pixel point as a background in the foreground image if the pixel point meets a background model of the point, and otherwise marking the corresponding pixel point as a foreground, namely a moving target.
7. The pedestrian boundary crossing detection method based on Gaussian mixture modeling according to claim 6, wherein the judgment of each pixel point comprises: firstly, initializing the mean value, standard deviation and weight of each Gaussian mixture model to obtain model initialization matrix parameters; acquiring a T frame image in a video, and obtaining a mean value and a standard of each pixel point by adopting an online EM algorithmTolerance and weight; detecting a newly read image frame, and sequencing each Gaussian kernel from large to small by dividing a weight w by a standard deviation sigma for each pixel point; then selecting the first B gaussians to ensure that
Eliminating noise points in the training process, wherein T is a set threshold; if only one Gaussian component in the pixel values of the current pixel point meets the following conditions:
is considered as a background point, where μiAnd (4) setting N as a mean value, updating the background image by using an online EM algorithm, and assigning the foreground as 255 and the background as 0 to obtain a foreground binary image.
8. The pedestrian boundary crossing detection method based on Gaussian mixture modeling of claim 7, wherein the morphological operations include removing isolated points remaining in the image and filling the void region by using morphological erosion and dilation operations on the foreground image.
9. The pedestrian boundary crossing detection method based on gaussian mixture modeling according to claim 8, wherein the removing of the small interference area of the non-pedestrian in the foreground image by the scale filter comprises counting the number of pixels in each small area, and removing the small non-attention area by the scale filter, wherein the size of the scale filter is set to 30.
10. The pedestrian boundary crossing detection method based on Gaussian mixture modeling according to claim 9, characterized in that a foreground proportion value, namely a foreground pixel area ratio value, of a moving target profile in a boundary crossing forbidden region is counted, when the foreground pixel area ratio value is larger than a set threshold value, a timer counts time, if the counted time is larger than the set threshold value, boundary crossing is judged, boundary crossing alarming is conducted, the boundary crossing alarming comprises an online marking alarm and a site alarming, the online marking alarm conducts online boundary crossing alarming recording according to a set safety mark, and the site alarming comprises a voice alarming device and a display prompting device; the voice warning device comprises a single chip microcomputer, a power supply module, a voice synthesizer, a loudspeaker and a wireless communication module, wherein the loudspeaker is electrically connected with the voice synthesizer, the single chip microcomputer controls the voice synthesizer to play set abnormal reminding voice through the loudspeaker, the power supply module comprises an EMI filter, a rectifier bridge and a DC-DC converter, the input end of the EMI filter is connected with a mains supply output end, the EMI filter, the rectifier bridge and the DC-DC converter are electrically connected in sequence, and the power supply module is used for providing required electric energy for the voice warning device; the display reminding device comprises an LED display screen and an LED display screen driver, the LED display screen driver is electrically connected with the LED display screen, and the LED display screen is used for displaying abnormal alarm data in a rolling mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110627647.7A CN113344874B (en) | 2021-06-04 | 2021-06-04 | Pedestrian boundary crossing detection method based on Gaussian mixture modeling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110627647.7A CN113344874B (en) | 2021-06-04 | 2021-06-04 | Pedestrian boundary crossing detection method based on Gaussian mixture modeling |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113344874A true CN113344874A (en) | 2021-09-03 |
| CN113344874B CN113344874B (en) | 2024-02-09 |
Family
ID=77474261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110627647.7A Active CN113344874B (en) | 2021-06-04 | 2021-06-04 | Pedestrian boundary crossing detection method based on Gaussian mixture modeling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113344874B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115482217A (en) * | 2022-09-21 | 2022-12-16 | 内蒙古科电数据服务有限公司 | Electric shock prevention video detection method for transformer substation based on Gaussian mixture model separation algorithm |
| CN115953872A (en) * | 2022-12-28 | 2023-04-11 | 广东悦视智能科技有限公司 | Pedestrian border crossing early warning method and device based on video monitoring and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102005062673A1 (en) * | 2005-12-23 | 2007-07-05 | Charité - Universitätsmedizin Berlin | Fluorochrome movement parameter determining method for computer based evaluation unit, involves calculating rate of deviation between simulated measurement series and associated series, and determining parameter from standard deviation |
| US20070206865A1 (en) * | 2006-03-02 | 2007-09-06 | Honeywell International Inc. | Block-based Gaussian Mixture Model video motion detection |
| CN101470809A (en) * | 2007-12-26 | 2009-07-01 | 中国科学院自动化研究所 | Moving object detection method based on expansion mixed gauss model |
| CN104318266A (en) * | 2014-10-19 | 2015-01-28 | 温州大学 | Image intelligent analysis processing early warning method |
| CN104680555A (en) * | 2015-02-13 | 2015-06-03 | 电子科技大学 | Border-crossing detection method and border-crossing monitoring system based on video monitoring |
| CN106327525A (en) * | 2016-09-12 | 2017-01-11 | 安徽工业大学 | Machine room important place border-crossing behavior real-time monitoring method |
| CN107705326A (en) * | 2017-09-15 | 2018-02-16 | 温州大学 | A kind of intrusion detection method that crosses the border in security sensitive region |
| DE102017212418A1 (en) * | 2017-07-20 | 2019-01-24 | Continental Automotive Gmbh | DRIVER ASSISTANCE SYSTEM AND METHOD FOR GUIDANCE PLANK RECOGNITION |
| CN110009650A (en) * | 2018-12-20 | 2019-07-12 | 浙江新再灵科技股份有限公司 | A kind of escalator handrail borderline region crosses the border detection method and system |
| CN110209068A (en) * | 2019-06-11 | 2019-09-06 | 滁州学院 | A kind of traffic lights timing designing and simulation method |
| CN111275910A (en) * | 2019-11-05 | 2020-06-12 | 杭州安脉盛智能技术有限公司 | Method and system for detecting border crossing behavior of escalator based on Gaussian mixture model |
-
2021
- 2021-06-04 CN CN202110627647.7A patent/CN113344874B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102005062673A1 (en) * | 2005-12-23 | 2007-07-05 | Charité - Universitätsmedizin Berlin | Fluorochrome movement parameter determining method for computer based evaluation unit, involves calculating rate of deviation between simulated measurement series and associated series, and determining parameter from standard deviation |
| US20070206865A1 (en) * | 2006-03-02 | 2007-09-06 | Honeywell International Inc. | Block-based Gaussian Mixture Model video motion detection |
| CN101470809A (en) * | 2007-12-26 | 2009-07-01 | 中国科学院自动化研究所 | Moving object detection method based on expansion mixed gauss model |
| CN104318266A (en) * | 2014-10-19 | 2015-01-28 | 温州大学 | Image intelligent analysis processing early warning method |
| CN104680555A (en) * | 2015-02-13 | 2015-06-03 | 电子科技大学 | Border-crossing detection method and border-crossing monitoring system based on video monitoring |
| CN106327525A (en) * | 2016-09-12 | 2017-01-11 | 安徽工业大学 | Machine room important place border-crossing behavior real-time monitoring method |
| DE102017212418A1 (en) * | 2017-07-20 | 2019-01-24 | Continental Automotive Gmbh | DRIVER ASSISTANCE SYSTEM AND METHOD FOR GUIDANCE PLANK RECOGNITION |
| CN107705326A (en) * | 2017-09-15 | 2018-02-16 | 温州大学 | A kind of intrusion detection method that crosses the border in security sensitive region |
| CN110009650A (en) * | 2018-12-20 | 2019-07-12 | 浙江新再灵科技股份有限公司 | A kind of escalator handrail borderline region crosses the border detection method and system |
| CN110209068A (en) * | 2019-06-11 | 2019-09-06 | 滁州学院 | A kind of traffic lights timing designing and simulation method |
| CN111275910A (en) * | 2019-11-05 | 2020-06-12 | 杭州安脉盛智能技术有限公司 | Method and system for detecting border crossing behavior of escalator based on Gaussian mixture model |
Non-Patent Citations (2)
| Title |
|---|
| 康杜;: "融合SCBP与改进混合高斯建模的运动物体检测方法", 电脑与信息技术, no. 01 * |
| 潘诚;覃祥孝;柯尊海;梁锴;罗宁;江蓓;: "船闸禁停线防越界智能监控***的研究与实现", 中国水运(下半月), no. 03 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115482217A (en) * | 2022-09-21 | 2022-12-16 | 内蒙古科电数据服务有限公司 | Electric shock prevention video detection method for transformer substation based on Gaussian mixture model separation algorithm |
| CN115482217B (en) * | 2022-09-21 | 2024-05-10 | 内蒙古科电数据服务有限公司 | Transformer substation electric shock prevention video detection method based on Gaussian mixture model separation algorithm |
| CN115953872A (en) * | 2022-12-28 | 2023-04-11 | 广东悦视智能科技有限公司 | Pedestrian border crossing early warning method and device based on video monitoring and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113344874B (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7106664B2 (en) | Intelligent driving control method and device, electronic device, program and medium | |
| JP5325899B2 (en) | Intrusion alarm video processor | |
| KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| CN107948465B (en) | A kind of method and apparatus that detection camera is disturbed | |
| CN100545867C (en) | Aerial shooting traffic video frequency vehicle rapid checking method | |
| CN105160297B (en) | Masked man's event automatic detection method based on features of skin colors | |
| CN103116985A (en) | Detection method and device of parking against rules | |
| CN113344874A (en) | Pedestrian boundary crossing detection method based on Gaussian mixture modeling | |
| CN111523397B (en) | Intelligent lamp post visual identification device, method and system and electronic equipment thereof | |
| CN113850123A (en) | Video-based road monitoring method and device, storage medium and monitoring system | |
| CN103605967A (en) | Subway fare evasion prevention system and working method thereof based on image recognition | |
| CN110441320B (en) | Coal gangue detection method, device and system | |
| Nodado et al. | Intelligent traffic light system using computer vision with android monitoring and control | |
| CN103049748B (en) | Behavior monitoring method and device | |
| CN111460917A (en) | Airport abnormal behavior detection system and method based on multi-mode information fusion | |
| Diaz-Cabrera et al. | Traffic light recognition during the night based on fuzzy logic clustering | |
| JP7125843B2 (en) | Fault detection system | |
| CN117294818A (en) | Building site panoramic monitoring method for airport construction | |
| JP3294468B2 (en) | Object detection method in video monitoring device | |
| CN106056060A (en) | Method and system for masked veil detection in video image | |
| Dong et al. | Detection method for vehicles in tunnels based on surveillance images | |
| CN112215109B (en) | Vehicle detection method and system based on scene analysis | |
| KR100967456B1 (en) | moving picture checking apparatus for an obstacle on a rail road crossing and method thereof | |
| JP2000023141A (en) | Moving object monitoring device | |
| KR101867869B1 (en) | Disaster response system based on street light |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |